rent-vs-buy

rent-vs-buy is a cursor rule for Cursor from mohitagw15856/pm-claude-skills. It costs 99 tokens per session (1,067 once invoked), scanned A, original, MIT.

A financial comparison of renting a home versus buying one. It tracks the owner's equity and selling costs alongside the renter's invested savings to find when one option overtakes the other.

In plain words
What is it for?
Use it to compare housing choices year by year, calculate the break-even time, and review assumptions such as mortgage terms, rent, investment returns, and expected stay.
Why use it?
Buying is often judged without counting transaction and ownership costs, while renting is often judged without counting investment of the monthly difference. This makes both paths use comparable assumptions.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/rent_vs_buy.py --price 450000 --rent 2200.

Good fit Use it to compare housing choices year by year, calculate the break-even time, and review assumptions such as mortgage terms, rent, investment returns, and expected stay.

Compare 6 cursor rules from other repositories ↓
About the project

PM Skills is a collection of plain-Markdown instructions that teach AI assistants structured methods for handling professional, personal, and life-admin tasks. People use it with Claude, ChatGPT, Gemini, Cursor, Codex, and other supported agents for work such as writing product requirements, reviewing documents, or planning difficult situations.

mohitagw15856/pm-claude-skills · 1,357 stars · on GitHub · mohitagw15856.github.io

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills
agentmods
npx agentmods add rules/mohitagw15856/pm-claude-skills/rent-vs-buy

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for rent-vs-buy

README.md
[![agentmods](https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/rent-vs-buy/github.svg)](https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/rent-vs-buy)
Your own site
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/rent-vs-buy"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/rent-vs-buy/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for rent-vs-buy

Your own site · 80×15
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/rent-vs-buy"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/rent-vs-buy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 99 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,067 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00099 $0.01067
Opus 5 $0.00049 $0.00534
Sonnet 5 $0.00020 $0.00213
Haiku 4.5 $0.00010 $0.00107

Measured 9d ago against content hash 2aae1854c830, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

rent-vs-buy scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

exports/cursor/pm-calculators/rent-vs-buy/rent-vs-buy.mdc · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rent vs Buy Skill

Rent-vs-buy arguments are usually two people comparing different questions: one counts equity and forgets transaction costs and carry; the other counts rent as "thrown away" and forgets the renter can invest the difference. This skill runs the symmetric model — both paths get their real costs and their real compounding — and delivers a breakeven horizon, because the honest answer is almost always "it depends how long you stay."

What This Skill Produces

  • The year-by-year table — owner net position (equity minus selling costs) vs renter net position (invested savings), per year
  • The breakeven year — before it, renting won; after it, buying won, on the stated assumptions
  • The assumption ledger — every input labeled, defaults flagged as defaults
  • The not-modeled list — taxes/deductions, renovation risk, the non-financials — stated up front

Required Inputs

Ask for these if not provided:

  • Home price and comparable monthly rent — same home, same neighborhood; comparing a condo rent to a house purchase is the classic apples-to-oranges error
  • Down payment %, mortgage rate, term (defaults 20% / 6.5% / 30yr, labeled)
  • How long they expect to stay — the single most decision-relevant input
  • Growth assumptions — appreciation, rent growth, investment return (defaults 3/3/5%, labeled)

Programmatic Helper

python3 scripts/rent_vs_buy.py --price 450000 --rent 2200
python3 scripts/rent_vs_buy.py --price 450000 --rent 2200 --horizon 10 --appreciation 2 --json

Deterministic. The renter's pot starts at the down payment + closing costs (the money a buyer parts with on day one) and each year absorbs the difference between owner outflow and rent. Selling costs are applied at every horizon — equity you can't access without paying 7% isn't fully yours.

Framework: The Symmetry Rules

  • The renter invests the difference — the model's load-bearing assumption; a renter who spends the difference makes buying win almost automatically, and that's a behavior question, not a math question. Say so.
  • Carry costs are real — tax, insurance, maintenance (~2%/yr of value) never build equity; "my mortgage is like rent" omits them
  • Transaction costs decide short horizons — ~3% in and ~7% out is why breakeven is measured in years, not months
  • Appreciation is an assumption, not a birthright — vary it before trusting a conclusion; a 1-point change often moves breakeven by years
  • The output is a horizon, not a verdict — "buying wins if you stay past year N" is the honest deliverable

Read the full file on GitHub · 77 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 77 lines · 99 tokens per session scan A 2aae1854c830

Subscribe to this mod's changes

rent-vs-buy is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,357 stars, last pushed yesterday), licensed MIT. It adds 99 tokens to every session and 1,067 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.